INDEX

Explanations

words related to connections and networking

oai_token-act-pair · gpt-3.5-turbo

terms related to connection or connectivity

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cheat

-0.69

Ħ¢

-0.66

 Ambrose

-0.66

 Clancy

-0.65

ãĥ£

-0.61

corn

-0.58

fare

-0.57

gery

-0.56

 Refuge

-0.54

inen

-0.54

POSITIVE LOGITS

icut

1.24

 dots

1.10

ioned

0.99

ivity

0.89

ions

0.88

 wire

0.86

later

0.82

 thereto

0.80

ications

0.77

 wires

0.76

Activations Density 0.059%

words related to connections and networking

terms related to connection or connectivity

No Comments

No Known Activations